CLIP Embedding Model

Class: ClipModelBlockV1

Source: inference.core.workflows.core_steps.models.foundation.clip.v1.ClipModelBlockV1

Use a CLIP model to create semantic embeddings of text and images.

This block accepts an image or string and returns an embedding. The embedding can be used to compare the similarity between different images or between images and text.

Type identifier

Use the following identifier in step "type" field: roboflow_core/clip@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Unique name of step in workflows.	❌
data	str	The string or image to generate an embedding for..	✅
version	str	Variant of CLIP model.	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to CLIP Embedding Model in version v1.

• inputs: Halo Visualization, Polygon Zone Visualization, Keypoint Detection Model, Label Visualization, Color Visualization, Clip Comparison, Relative Static Crop, VLM as Classifier, CSV Formatter, Stability AI Image Generation, Florence-2 Model, Circle Visualization, Roboflow Dataset Upload, LMM For Classification, Depth Estimation, Absolute Static Crop, Perspective Correction, Twilio SMS Notification, Google Gemini, Slack Notification, Grid Visualization, Image Preprocessing, Image Blur, Classification Label Visualization, Email Notification, Local File Sink, Image Contours, Florence-2 Model, Instance Segmentation Model, Reference Path Visualization, Google Vision OCR, SIFT, Llama 3.2 Vision, Multi-Label Classification Model, Keypoint Visualization, CogVLM, SIFT Comparison, Ellipse Visualization, Roboflow Dataset Upload, Triangle Visualization, Line Counter Visualization, Dot Visualization, Mask Visualization, Dynamic Crop, Object Detection Model, Stitch Images, Webhook Sink, Pixelate Visualization, Image Threshold, Corner Visualization, Roboflow Custom Metadata, OpenAI, Model Comparison Visualization, Camera Calibration, Blur Visualization, Stability AI Inpainting, Camera Focus, Image Slicer, OpenAI, Trace Visualization, Bounding Box Visualization, Stability AI Outpainting, Crop Visualization, Stitch OCR Detections, Anthropic Claude, OpenAI, Single-Label Classification Model, Image Slicer, Model Monitoring Inference Aggregator, LMM, OCR Model, VLM as Detector, Image Convert Grayscale, Background Color Visualization, Polygon Visualization
• outputs: Identify Changes, Cosine Similarity, Identify Outliers

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds CLIP Embedding Model in version v1 has.

Bindings

• input

  • data (Union[string, image]): The string or image to generate an embedding for..
  • version (string): Variant of CLIP model.

• output

  • embedding (embedding): A list of floating point numbers representing a vector embedding..

Example JSON definition of step CLIP Embedding Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/clip@v1",
    "data": "$inputs.image",
    "version": "ViT-B-16"
}